论文简读《Exploring Categorical Regularization for Domain Adaptive Object Detection》
https://arxiv.org/pdf/2003.09152.pdf提出类别正则化框架，主要使用多标签分类来进行实现前景物体的弱监督。It is widely acknowledged that CNNs trained for singlelabel image classification tend to produce high responses on the local regions containing the main objects [38, 40, 39]. Analog
